Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 919 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2380. Min Range: -2.2380

Max Act: 2.2380. Min Act: -0.0000

Data Index: 708762 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.9420. Min Act: -0.0000

Data Index: 1200846 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.9217. Min Act: -0.0000

Data Index: 112668 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.8860. Min Act: -0.0000

Data Index: 585409 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.7150. Min Act: -0.0000

Data Index: 805089 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.6198. Min Act: -0.0000

Data Index: 732012 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.7034. Min Act: -0.0000

Data Index: 1160752 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.7649. Min Act: -0.0000

Data Index: 22693 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.6667. Min Act: -0.0000

Data Index: 1161354 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.6437. Min Act: -0.0000

Data Index: 1273432 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.5606. Min Act: -0.0000

Data Index: 455964 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.5688. Min Act: -0.0000

Data Index: 1106668 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.4349. Min Act: -0.0000

Data Index: 109039 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.4323. Min Act: -0.0000

Data Index: 508554 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.5283. Min Act: -0.0000

Data Index: 50549 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.4077. Min Act: -0.0000

Data Index: 81587 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.4363. Min Act: -0.0000

Data Index: 624151 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.4565. Min Act: -0.0000

Data Index: 141273 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.5078. Min Act: -0.0000

Data Index: 4271 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 2.2380. Min Range: -2.2380

Max Act: 1.3563. Min Act: -0.0000

Data Index: 165472 (C4 (Web Text))

Max Activating Token Index: 282